© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 93809
    Prev
    Next
    INDEX
    Explanations

    People's names/nationalities suffixes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SequentialGroup
    -0.80
    SpringBootTest
    -0.64
    +#+#
    -0.64
    modelBuilder
    -0.63
    tifies
    -0.60
    extAlignment
    -0.58
    GEBURTSDATUM
    -0.57
     fédé
    -0.57
    //
    -0.54
     صوتيه
    -0.54
    POSITIVE LOGITS
     themselves
    0.85
     everywhere
    0.79
     were
    0.74
     are
    0.73
     believe
    0.70
     aren
    0.69
     like
    0.68
    themselves
    0.68
     have
    0.68
     weren
    0.64
    Activations Density 0.001%

    No Known Activations